- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes FGPO, a feasibility-gated preference optimization framework for video super-resolution. FGPO combines multi-objective evaluation and Pareto selection with LR-guided spatiotemporal dispersion estimation to construct spatially adaptive diversity rewards. The framework supports different preference optimization algorithms. Experiments on four VSR benchmarks demonstrate improvements in reconstruction fidelity, temporal consistency, and perceptual quality.
Critical strengths
- Well-motivated framework. FGPO addresses the challenge of balancing structural fidelity and perceptual quality through feasibility-gated selection and spatially adaptive rewards. The overall design is intuitive and practically meaningful.
- Strong experimental performance. FGPO achieves consistent improvements across multiple VSR benchmarks. The extensive ablations, human evaluations, and experiments with different optimization algorithms further support its effectiveness.
Critical weaknesses
- Insufficient justification of dispersion-based uncertainty estimation. The method assumes that high inter-candidate dispersion indicates regions where additional detail exploration is beneficial. However, such dispersion may also arise from sampling instability or structural artifacts. The existing experiments do not sufficiently establish that dispersion reliably reflects plausible reconstruction ambiguity.
- Limited generalizability validation and incomplete baseline comparisons. Although FGPO supports different optimization algorithms, experiments are primarily conducted on a single Wan2.1-based backbone. Evaluation on additional VSR architectures would better support its generality. Moreover, competitive recent methods such as DOVE (NeurIPS 2025) are missing from the main comparisons.
- Insufficient temporal consistency evaluation. Temporal consistency is a central motivation, but the quantitative evaluation mainly relies on VBench Subject Consistency, which does not directly measure temporal flickering or motion-compensated consistency. Additional objective temporal metrics would strengthen the conclusions, despite the supplementary human evaluation.
Questions for authors
- Can the authors provide stronger evidence that high candidate dispersion corresponds to plausible reconstruction ambiguity rather than sampling artifacts or structural errors?
- Can FGPO be evaluated on additional VSR backbones, and can the authors include DOVE under consistent evaluation protocols?
- Can the authors provide additional temporal consistency metrics, such as temporal warping error or flickering measures, to support the claimed improvements?
5 comments
Response to Weaknesses 2 & Questions 2 – Part2
W2 & Q2:Validation of framework generalizability across video backbones and additional quantitative comparison with DOVE.
A2: We thank the reviewer for the constructive suggestions. We additionally evaluated FGPO on CogVideox[1] and conducted a comparison against the recent DOVE[2] under strictly identical evaluation protocols on YouHQ-40. As shown in the table below, transferring FGPO to the CogVideo backbone consistently yields improvements across all fidelity and perceptual metrics. Meanwhile, under strictly identical testing environments, the FGPO variants based on both Wan2.1 and CogVideox outperform DOVE across full-reference fidelity metrics as well as temporal consistency and overall perceptual quality. This demonstrates that FGPO achieves superior performance across different backbones, and we have incorporated these extended evaluations into Appendix R of the revised manuscript, which has been highlighted in red.
Table R2: Quantitative evaluation of framework generalizability across video backbones and comparison with DOVE on YouHQ-40.
| Method | PSNR () | SSIM () | LPIPS () | VBench-SC () | VBench-IQ () | VBench-AQ () |
|---|---|---|---|---|---|---|
| DOVE (NeurIPS 2025) | 23.750 | 0.665 | 0.320 | 0.972 | 0.738 | 0.572 |
| Base Model (CogVideox) | 22.850 | 0.612 | 0.355 | 0.965 | 0.718 | 0.550 |
| FGPO (Ours, on CogVideox) | 24.380 | 0.695 | 0.284 | 0.977 | 0.755 | 0.586 |
| Base Model (Wan2.1) | 22.255 | 0.594 | 0.364 | 0.970 | 0.732 | 0.565 |
| FGPO (Ours, on Wan2.1) | 24.562 | 0.702 | 0.275 | 0.979 | 0.762 | 0.592 |
[1]Cogvideox: Text-to-video diffusion models with an expert transformer. ICLR2025.
[2]Dove: Efficient one-step diffusion model for real-world video super-resolution. NeurIPS 2025
Response to Weaknesses 3 & Questions 3 – Part3
W3 & Q3:Additional objective temporal metrics for motion-compensated warping error and temporal flickering across synthetic and real-world benchmarks.
A3: We thank the reviewer for the constructive suggestions. We conducted extended evaluations across both synthetic (YouHQ-40) and real-world (VideoLQ-50) benchmarks using two standard objective temporal metrics: (1) Temporal Warping Error, which calculates the MAE of motion-compensated pixel alignment between frames after occlusion masking using RAFT optical flow; and (2) Temporal Flickering Score, which quantifies high-frequency luminance fluctuation rates along motion trajectories. As shown in the table below, FGPO achieves optimal temporal stability: on YouHQ-40, compared to the Base Model, both Temporal Warping Error (1.32 vs. 2.15) and Temporal Flickering Score (1.41 vs. 2.42) are substantially reduced, outperforming other methods including DOVE; on real-world VideoLQ-50, FGPO similarly strongly suppresses temporal issues induced by complex degradations (1.62 vs. 2.45). We have included these metrics in Appendix S of the revised manuscript, which has been highlighted in red.
Table R3: Objective temporal stability evaluation across synthetic (YouHQ-40) and real-world (VideoLQ-50) benchmarks.
| Method | YouHQ-40: Temporal Warping Error () | YouHQ-40: Temporal Flickering Score () | VideoLQ-50: Temporal Warping Error () | VideoLQ-50: Temporal Flickering Score () |
|---|---|---|---|---|
| DOVE | 1.75 | 1.92 | 2.05 | 2.31 |
| SeedVR2 | 2.42 | 2.85 | 2.81 | 3.25 |
| FlashVSR | 1.82 | 2.10 | 2.12 | 2.50 |
| PS-SR | 1.68 | 1.88 | 1.98 | 2.22 |
| SparkVSR | 1.78 | 1.95 | 2.08 | 2.38 |
| OSDEnhancer | 1.85 | 2.05 | 2.15 | 2.42 |
| Base Model | 2.15 | 2.42 | 2.45 | 2.92 |
| FGPO (Ours) | 1.32 | 1.41 | 1.62 | 1.75 |
Response to Weaknesses 1 & Questions 1 – Part1
We would like to sincerely thank the reviewer for the detailed and constructive comments on our work. We take every comment seriously and hope our response can address the reviewer’s concerns. If there are any remaining questions, we are more than happy to address them.
W1 & Q1:Evidence that high candidate dispersion reflects plausible visual ambiguity rather than generative artifacts or structural errors.
A1: We thank the reviewer for the constructive suggestions. FGPO defines candidate dispersion as empirical candidate discrepancy within the generative hypothesis space, rather than strict Bayesian posterior uncertainty; meanwhile, through dual evidence from architectural safeguards and regional quantitative diagnostics, we confirm that this discrepancy strictly reflects plausible reconstruction ambiguity, rather than sampling artifacts or structural errors. Architecturally, feasibility gating pre-filters structural collapse and inter-frame flickering (qD or qT<τ) prior to reward allocation, while ST-GF uses the LR luminance anchor (y↑Y) to strictly confine high dispersion to under-constrained texture regions, while smoothing localized sampling noise and suppressing boundary leakage. Empirically, the pixel-wise Pearson correlation coefficient between the spatial mask M and objective artifact proxy maps is extremely low (ρ≤0.09, Appendix O.3).
Furthermore, as shown in the table below, fine-grained regional results across high-mask and low-mask regions demonstrate that low-mask regions maintain near-perfect LR structural consistency and extremely low temporal warping error (computed as occlusion-masked frame-to-frame warping MAE via RAFT optical flow), whereas high-mask regions, while exhibiting moderate and controllable discrepancy, maintain an equally minimal artifact defect score (evaluating patch-level defect probabilities via a fine-tuned evaluator following VBench-IQ standards) and achieve high human visual plausibility acceptance, proving that the candidate discrepancy corresponds to rich and realistic detail synthesis rather than generative errors. We have supplemented these experimental results into Appendix Q of the revised manuscript, which has been highlighted in red.
Table R1: Fine-grained quantitative diagnostic analysis across spatial region partitions.